Malte Pietsch

Oh great, that's even better :) Could you convert the model to PyTorch / transformers format? We are actually planning to index the CORD-19 dataset in elasticsearch and use [haystack](https://github.com/deepset-ai/haystack/)...

Great! Thanks for sharing your data. > Would love to have the additional dataset to continue training. Would you also be able to add a script to convert it to...

Nice, good finding @ViktorAlm. From a quick look, this dataset seems to contain many question-answer pairs, but is lacking the "context" text as it's rather extracted from FAQ websites. Not...

The Telegram Bot was implemented by @theapache64. Maybe he can help you here ...

Great idea. @stedomedo! Did I get this right, that we would still need language-specific models for question similarity with this approach? Would it be an alternative to translate the user...

Hey @Peter-Pansen, Do you mean the Telegram bot? @theapache64 is the main contact person for this. Could you describe a bit what type of feedback button you had in mind?...

If you are looking for an actively maintained alternative, maybe [haystack](https://github.com/deepset-ai/haystack/) is an option for you. We'd love to welcome you in our community :heart: I think @andrelmfarias did an...

Great, thanks @fmikaelian :+1:

Maybe just a PyCharm issue then :thinking: . Could someone else with PyCharm try this one out?

Interesting idea, but I agree with @bogdankostic that leveraging elastic's existing components (e.g. stemmer, synoynms, analyzer ...) will probably be more scalable and meaningful. This has the advantage that everything...